{"id":"https://openalex.org/W2146585945","doi":"https://doi.org/10.1145/1141277.1141524","title":"Using the structure of documents to improve the discovery of unexpected information","display_name":"Using the structure of documents to improve the discovery of unexpected information","publication_year":2006,"publication_date":"2006-04-23","ids":{"openalex":"https://openalex.org/W2146585945","doi":"https://doi.org/10.1145/1141277.1141524","mag":"2146585945"},"language":"en","primary_location":{"id":"doi:10.1145/1141277.1141524","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1141277.1141524","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2006 ACM symposium on Applied computing","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5029553022","display_name":"Fran\u00e7ois Jacquenet","orcid":"https://orcid.org/0000-0002-0653-0710"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Fran\u00e7ois Jacquenet","raw_affiliation_strings":["University of Saint-Etienne, Saint-Etienne, France"],"affiliations":[{"raw_affiliation_string":"University of Saint-Etienne, Saint-Etienne, France","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086633120","display_name":"Christine Largeron","orcid":"https://orcid.org/0000-0003-1059-4095"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Christine Largeron","raw_affiliation_strings":["University of Saint-Etienne, Saint-Etienne, France"],"affiliations":[{"raw_affiliation_string":"University of Saint-Etienne, Saint-Etienne, France","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5029553022"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.78593137,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.79343109,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1036","last_page":"1042"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9986000061035156,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9986000061035156,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9846000075340271,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9785000085830688,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7600426077842712},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6885831356048584},{"id":"https://openalex.org/keywords/work","display_name":"Work (physics)","score":0.49345341324806213},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.35237520933151245},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3413935899734497},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10546451807022095}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7600426077842712},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6885831356048584},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.49345341324806213},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.35237520933151245},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3413935899734497},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10546451807022095},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1141277.1141524","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1141277.1141524","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2006 ACM symposium on Applied computing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4300000071525574,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1481997832","https://openalex.org/W1533703978","https://openalex.org/W1597618577","https://openalex.org/W1638133288","https://openalex.org/W1956559956","https://openalex.org/W2024060531","https://openalex.org/W2034701578","https://openalex.org/W2088750139","https://openalex.org/W2106490129","https://openalex.org/W2135909747","https://openalex.org/W2149111705","https://openalex.org/W2325227998","https://openalex.org/W2481930235","https://openalex.org/W2758584545","https://openalex.org/W6628747921","https://openalex.org/W6635540155","https://openalex.org/W6640862754"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W4402327032","https://openalex.org/W2382290278"],"abstract_inverted_index":{"In":[0],"this":[1],"paper":[2],"we":[3,47],"are":[4,68,75,82],"interested":[5],"in":[6,21,33,88],"taking":[7,54],"into":[8,55],"account":[9,56],"the":[10,13,16,34,40,43,51,57,60,66,86,89,113,117,121,124,127],"structure":[11,58,125],"of":[12,18,42,45,59,65,105,123,126],"documents":[14,61,67],"during":[15],"discovery":[17],"unexpected":[19,99],"information":[20,100],"textual":[22],"databases.":[23],"Following":[24],"a":[25,95],"work":[26],"that":[27],"aimed":[28],"at":[29],"designing":[30],"and":[31,112],"integrating,":[32],"UnexpectedMiner":[35],"system,":[36],"some":[37,71,98],"measures":[38,91],"for":[39],"evaluation":[41],"unexpectedness":[44,90],"documents,":[46],"wanted":[48],"to":[49,92],"improve":[50],"system":[52,87,108],"by":[53,70,77,85,120],"processed.":[62],"Each":[63],"part":[64],"weighted":[69],"coefficients":[72,81],"whose":[73],"values":[74],"determined":[76],"optimization":[78],"techniques.":[79],"Those":[80],"then":[83,110],"used":[84],"determine":[93],"if":[94],"document":[96],"contains":[97],"or":[101],"not.":[102],"The":[103],"efficiency":[104],"our":[106],"new":[107],"is":[109],"evaluated":[111],"experiments":[114],"put":[115],"forward":[116],"improvements":[118],"induced":[119],"use":[122],"documents.":[128]},"counts_by_year":[{"year":2018,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}